Computers & Industrial Engineering最新文献

{"title":"The emergency location-routing problem with facilities sharing and evacuation","authors":"Guiqin Xue ,&nbsp;Zheng Wang","doi":"10.1016/j.cie.2025.111321","DOIUrl":"10.1016/j.cie.2025.111321","url":null,"abstract":"<div><div>This paper addresses an emergency location-routing problem encompassing facility sharing and evacuation within an emergency response system. We develop an integrated network combining an emergency response center, two disaster site types, and two emergency facility types. A differentiated time window distinguishes the rescue time sensitivity of the two disaster site types, while a time-dependent psychological cost function assesses the psychological impact on victims. The Bureau of Public Roads (BPR) road resistance function is adapted to evaluate post-disaster traffic capacity. The problem is formulated as a mixed integer programming model to minimize the facility opening, emergency vehicle travel, and victims’ time-dependent psychological costs. We investigate the model’s analytical properties and construct several valid inequalities. Seven problem-specific route generation heuristics are proposed to warm start the set partitioning model, yielding high-quality emergency vehicle routes. Numerical experiments on small- and medium-scale instances validate the performance of the proposed method. The three strategies for comparison, evaluated using cases from Xi’an, China, demonstrate that our method achieves a reasonable balance between fairness and efficiency.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111321"},"PeriodicalIF":6.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144366794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Post-warranty strategies and pricing decisions in a dual-channel supply chain considering channel competition","authors":"Min Wang,&nbsp;Jia-Yi Zhang,&nbsp;Guang-Xin Gao","doi":"10.1016/j.cie.2025.111322","DOIUrl":"10.1016/j.cie.2025.111322","url":null,"abstract":"<div><div>Inspired by evidence regarding Gree’s superlong free-repair warranty services and considering channel competition, this study examines post-warranty strategies, i.e., providing extended or free-repair warranty services in the post-warranty period, in a single-manufacturer–single-retailer dual-channel supply chain. Based on a game-theoretical model, we optimize the warranty and pricing decisions of supply chain members under two post-warranty strategies and perform a comprehensive analysis. Some key findings are generated. First, the results show the interactive influence of the proportion of direct-channel buyers and the cost coefficient of warranty services, which are explained by the bullwhip effect and cost-benefit trade-off of warranty services. Second, by comparing supply chain members’ profits under the two post-warranty strategies, we find that whether the manufacturer should provide extended or free-repair warranty services depends on the cost coefficient of warranty services. Meanwhile, the retailer and the supply chain may suffer losses due to the manufacturer’s implementation of the optimal post-warranty strategy. Therefore, we recommend adopting transfer payment mechanisms for supply chain coordination. We further discuss single-channel scenarios and find that the manufacturer will always provide extended warranty services. This finding highlights the influence of the channel structure on the optimal post-warranty strategy and the significance of the free-repair warranty.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111322"},"PeriodicalIF":6.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144471298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent scheduling of urban rail transit loop line trains: A study on coordinated optimization of timetables and rolling stock circulation plans based on DQN deep reinforcement learning","authors":"Qiuhan Dong ,&nbsp;Jinjin Tang ,&nbsp;Wen-Long Shang ,&nbsp;Xinyun Shao ,&nbsp;Mikela Chatzimichailidou","doi":"10.1016/j.cie.2025.111297","DOIUrl":"10.1016/j.cie.2025.111297","url":null,"abstract":"<div><div>Unlike in non-loop urban rail transit lines where the connection between trains is accomplished through turnaround operations, on loop lines, after reaching the terminal station, trains do not undertake turnaround operations but continue running in the same direction to complete the connection. Hence, it is necessary to reconfigure the model and algorithm to accommodate the operational characteristics of trains on loop lines. This paper categorizes the stations on loop lines into reference stations and non-reference stations based on the characteristics of loop lines, and determines the spatiotemporal paths of train connection operations on loop lines according to the reference stations. This paper is the first to address the collaborative optimization problem of timetable and rolling stock circulation plan for loop lines. It analyzes the characteristics of train arrival and departure operations, stop operations, and connection operations on loop lines, and innovatively establishes the correlations among the timetables, rolling stock circulation plans, and various train operations through a mathematical model. Based on the model characteristics, the conditions for the existence of the optimal solution when the headway is determined and the deterministic solution method are derived. A Deep Q-Network (DQN) is used to determine the optimal headway. The FSAE-LL (Fast Solution Algorithm for Engineering-Loop Line) algorithm is proposed by integrating the deterministic search method with the DQN. Finally, a numerical experiment is conducted using a loop line in a certain city in Southwest China. The loop line operation diagram is optimized using the FSAE-LL algorithm and the genetic algorithm respectively. The results indicate that the optimization results of the FSAE-LL algorithm save 4.3% of the total cost and 27.9% of the solution time compared to those of the genetic algorithm, verifying the feasibility and validity of the theory proposed in this paper.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111297"},"PeriodicalIF":6.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated support vector machine with improved PSO optimization for early risk screening and prevention of stroke in patients with hypertension","authors":"Gang Du ,&nbsp;Ranran Ou","doi":"10.1016/j.cie.2025.111300","DOIUrl":"10.1016/j.cie.2025.111300","url":null,"abstract":"<div><div>Hypertension is a significant global health threat, and stroke is the leading cause of death and disability worldwide. Therefore, early risk identification is crucial for stroke prevention in patients with hypertension. This study proposes an integrated approach using a support vector machine optimized by a two-stage adaptive particle swarm optimization algorithm for the early risk screening of stroke in patients with hypertension. We collected medical data from Shanghai First People’s Hospital and used machine learning to construct a predictive model. The support vector machine served as the base model, and the two-stage adaptive particle swarm optimization algorithm performed parameter optimization, enhancing the model’s classification accuracy and computational efficiency. This improved algorithm achieved an accuracy of 0.8905, outperforming standard support vector machines, genetic algorithm support vector machines, and grid search-support vector machine algorithms. Compared with other methods, our model demonstrated superior prediction accuracy and generalization ability, which are essential for the early screening and prevention of stroke in patients with hypertension. This study contributes to the advancement of medical services for stroke prevention in patients with hypertension and provides a model for effective health management.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111300"},"PeriodicalIF":6.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144288671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncovering the semiconductor industry’s hidden secret to success: A shapley-values-guided dynamic network data envelopment analysis integrating eXtreme gradient boosting","authors":"Chen-Hsiang Hong,&nbsp;Ruey-Shan Guo,&nbsp;Chialin Chen","doi":"10.1016/j.cie.2025.111284","DOIUrl":"10.1016/j.cie.2025.111284","url":null,"abstract":"<div><div>The semiconductor industry, a foundation of the modern economy, demands integrated evaluation approaches that consider financial, technological, and operational dimensions together. However, existing methods often address these aspects in isolation, limiting comprehensive understanding. This study proposes a novel SHAP-value-based performance evaluation framework that combines eXtreme Gradient Boosting (XGBoost) with dynamic network Data Envelopment Analysis (DEA). Unlike traditional uses of SHAP for post hoc interpretation, we employ SHAP as a pre-analysis tool to systematically select variables and allocate stage-specific linkage ratios, objectively quantifying the influence of each dimension on firm performance. Furthermore, by dynamically recalculating SHAP values across different periods, our model captures temporal shifts in factor importance — a capability not addressed in conventional network or dynamic DEA approaches.</div><div>This dynamic design makes the framework particularly well-suited for analyzing changes across different market conditions, especially during downturns, where successful firms may adopt distinct strategic decisions compared to failing ones. By tracking how the importance of financial, technological, and operational variables evolves over time, the model provides insights into critical success factors under varying external shocks. While this study uses the Covid-19 pandemic as a demonstration case, the framework may be applicable to other disruption scenarios. Overall, this research bridges critical methodological gaps and offers a robust tool for strategic decision-making in highly volatile industries.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111284"},"PeriodicalIF":6.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Backup production decisions and financing strategies of a capital-constrained supplier with supply disruption","authors":"Peng Ma ,&nbsp;Zhen Wu ,&nbsp;Yuzhuo Qiu ,&nbsp;Jie Cao ,&nbsp;Ming Liu","doi":"10.1016/j.cie.2025.111311","DOIUrl":"10.1016/j.cie.2025.111311","url":null,"abstract":"<div><div>With the frequency of sudden disasters, global supply chains are at risk of supply disruption. Backup production is an appropriate but costly method for supply chains to solve supply disruption problems. However, few studies have taken into account that suppliers may face capital-constrained problems in the event of supply disruption, which limits their abilities to adopt backup production during the supply disruption. This research examines a supply chain scenario where the capital-constrained supplier encounters the risks of supply disruptions and explores the effects of various backup production decisions and financing strategies. We demonstrate that with large potential market size, the capital-constrained supplier will adopt manufacturer financing with backup production to mitigate his financial pressure, and the manufacturer will offer financing to the capital-constrained supplier. With the small potential market size, when selecting bank financing without backup production, the supplier will achieve the highest profits, but the manufacturer will not offer financing to the capital-constrained supplier. Moreover, the manufacturer cannot obtain higher profits with backup production adoption and high unit production cost. These insights highlight the critical relationship between financing strategies and backup production in enhancing supply chain’s resilience.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111311"},"PeriodicalIF":6.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144366796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Supply chain demand forecasting based on multi-time scale data fusion network","authors":"Yipeng Chen,&nbsp;Heng Zhang,&nbsp;Xingyou Yan,&nbsp;Qiang Miao","doi":"10.1016/j.cie.2025.111324","DOIUrl":"10.1016/j.cie.2025.111324","url":null,"abstract":"<div><div>Demand forecasting is crucial in supply chain management. However, the supply chain has grown increasingly complex and uncertain due to the expansion of mass manufacturing. Presently, prevailing supply chain demand forecasting methods primarily rely on traditional statistical models or single time scale models, resulting in inadequate forecasting performance. This paper proposes a novel supply chain demand forecasting model that employs multi-time scale data fusion to enhance forecasting performance. Initially, three parallel temporal convolutional networks are constructed to extract feature information from three different time scales of data. Following that, a feature fusion method is devised utilizing autoencoders and attention mechanism. The method reconstructs data through autoencoders, unifying the time dimension of features while enhancing them. It then adaptively calculates weights for different time scales using an attention mechanism and combines the reconstructed data with corresponding weights to obtain features containing information from various time scales. Subsequently, the proposed model further maps the fused data using temporal convolutional networks to obtain the final prediction output. Finally, this paper validates the model using data provided by a major home appliance manufacturer and compares it with various advanced time series forecasting models, demonstrating the superiority of the proposed model. The ablation experiments assess the effectiveness and necessity of the multi-time scale model input and fusion module on forecast results, confirming the superiority and necessity of the multi-time scale data input and fusion module.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111324"},"PeriodicalIF":6.7,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144291089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing multi-vehicle inventory routing problem for waste collection with overflow-level-dependent service times in bins","authors":"Isaías Sepúlveda-Campos ,&nbsp;Carlos Obreque ,&nbsp;Gonzalo Méndez-Vogel","doi":"10.1016/j.cie.2025.111323","DOIUrl":"10.1016/j.cie.2025.111323","url":null,"abstract":"<div><div>The growth of urbanization leads to an increase in waste generation in cities. One policy adopted by municipalities for waste management is to provide bins for citizens to dispose of their garbage. However, limited resources can make proper waste management difficult and, together with the population’s behavior, lead to undesirable situations, such as the formation of overflows in bins. When this occurs, collection times vary because operators must clean the site using hand tools. In this study, we approach urban waste collection from bins as a Multi-vehicle Inventory Routing Problem, considering the variability in service times due to overflow. We formulate a mixed integer nonlinear programming model, to which we apply linearization techniques to propose two new linear reformulations. These are solved using a branch-and-cut algorithm, aiming to balance economic and environmental costs by minimizing transportation and overflow costs. The models are compared with each other and the best performing one is selected based on preliminary experiments. This model can optimally solve for medium-sized instances, and the results demonstrate the importance of considering variability in service times in overflow bins, as it is a factor that produces changes in the determination of collection routes.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111323"},"PeriodicalIF":6.7,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144519153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of supply disruption frequency and severity on order and costs in an interdependent supply–demand newsvendor","authors":"Yan Weng ,&nbsp;Li Xiao","doi":"10.1016/j.cie.2025.111248","DOIUrl":"10.1016/j.cie.2025.111248","url":null,"abstract":"<div><div>In the context of global supply disruption events, such as the COVID-19 pandemic, it is imperative to investigate the intricate relationship between random supply and uncertain demand and its impact on operational decisions and system performances. In this paper, we focus on a Newsvendor model, where random supply and uncertain demand are intricately interconnected through an underlying state variable. Specifically, we evaluate the influence of disruption frequency and disruption severity in the context of the dependent supply–demand structure. Our investigation highlight the disparate effects of these factors under positive and negative dependence scenarios. Moreover, the optimal cost exhibits a non-monotonic behavior with respect to disruption frequency or severity. One managerial implication that arises from our study is that optimal cost is minimized when the gap of supply–demand dependent structures under different states vanishes.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111248"},"PeriodicalIF":6.7,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144262855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GIS-integrated optimization approaches for the culvert maintenance planning and scheduling problem","authors":"Zefeng Lyu ,&nbsp;Christopher Starr ,&nbsp;Andrew Junfang Yu","doi":"10.1016/j.cie.2025.111318","DOIUrl":"10.1016/j.cie.2025.111318","url":null,"abstract":"<div><div>Culvert preservation is essential for extending the lifecycle of these critical infrastructure components. Given the limited annual budgets for maintenance and rehabilitation, it is not feasible to maintain all culverts at optimal performance. Traditional system-level maintenance approaches are often too broad and not cost-effective due to the complexity of culverts, which consist of various components such as barrels, endwalls, junctions, and energy dissipation devices. To address these challenges, this paper proposes a comprehensive framework for optimizing culvert maintenance decisions. A mathematical model and a genetic algorithm are introduced to solve the problem, considering budget limitations, available labor, and other operational constraints. The GIS system is used for extracting spatial information, calculating grouping discounts, and visualizing results. The computational results show that the mathematical model performs well, solving all instances to optimality within seconds. The GA serves as an alternative approach, particularly in cases where a self-contained method is required or where further solution improvement is desired. Using Anderson County as a case study, three key findings are observed: increasing the grouping size for high-requirement jobs improves efficiency, available person-hours significantly impact the choice between in-house and contractor work, and budget increases show diminishing returns after a certain threshold. The findings of this research can help the Tennessee Department of Transportation (TDOT) make more informed and cost-effective decisions regarding culvert maintenance.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"207 ","pages":"Article 111318"},"PeriodicalIF":6.7,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144471237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}